Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1418 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.8800. Min Act: -0.0000

Data Index: 1197967 (The Pile)

Max Activating Token Index: 988

Text #1

Max Range: 1.0509. Min Range: -1.0509

Max Act: 1.0509. Min Act: -0.0000

Data Index: 97417 (The Pile)

Max Activating Token Index: 25

Text #2

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.9741. Min Act: -0.0000

Data Index: 916658 (The Pile)

Max Activating Token Index: 530

Text #3

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.9316. Min Act: -0.0000

Data Index: 1868661 (The Pile)

Max Activating Token Index: 375

Text #4

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.8407. Min Act: -0.0000

Data Index: 733691 (The Pile)

Max Activating Token Index: 67

Text #5

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.8477. Min Act: -0.0000

Data Index: 199784 (The Pile)

Max Activating Token Index: 79

Text #6

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.9281. Min Act: -0.0000

Data Index: 1853069 (The Pile)

Max Activating Token Index: 757

Text #7

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.8307. Min Act: -0.0000

Data Index: 1698238 (The Pile)

Max Activating Token Index: 497

Text #8

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7600. Min Act: -0.0000

Data Index: 585979 (The Pile)

Max Activating Token Index: 93

Text #9

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7715. Min Act: -0.0000

Data Index: 1596170 (The Pile)

Max Activating Token Index: 305

Text #10

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7607. Min Act: -0.0000

Data Index: 1490704 (The Pile)

Max Activating Token Index: 355

Text #11

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.8037. Min Act: -0.0000

Data Index: 644820 (The Pile)

Max Activating Token Index: 997

Text #12

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7955. Min Act: -0.0000

Data Index: 1351076 (The Pile)

Max Activating Token Index: 385

Text #13

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7912. Min Act: -0.0000

Data Index: 443746 (The Pile)

Max Activating Token Index: 1000

Text #14

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7303. Min Act: -0.0000

Data Index: 1033977 (The Pile)

Max Activating Token Index: 941

Text #15

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7114. Min Act: -0.0000

Data Index: 22554 (The Pile)

Max Activating Token Index: 937

Text #16

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.6609. Min Act: -0.0000

Data Index: 1828400 (The Pile)

Max Activating Token Index: 876

Text #17

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.6685. Min Act: -0.0000

Data Index: 1869432 (The Pile)

Max Activating Token Index: 285

Text #18

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1266436 (The Pile)

Max Activating Token Index: 491

Text #19

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1584208 (The Pile)

Max Activating Token Index: 793